Mining Traversal Patterns on the Www: Using a Meaningful Candidate Approach

Since the World Wide Web appeared, more and more useful information has been available on the WWW. In order to find the hidden information, one application of data mining on the WWW, referred to as Web mining, has become a research area with increasing importance. Mining traversal patterns is one of the important topics in Web mining. It focuses on how to find the Web page sequences which are frequently browsed by users. Mining such information could help webmasters improve the structure of Web sites or make better marketing strategies in an e-commerce environment. Although traditional algorithms for mining association rules could be applied to mine traversal patterns, they may generate too many invalid candidate patterns and do not work efficiently. This book, therefore, provides three new algorithms for mining traversal patterns. These algorithms make use of the property of Web transactions and generate meaningful candidate patterns. Moreover, they apply several techniques to decrease the times of database scan. Therefore, they could provide better performance than traditional algorithms in terms of processing time.